I believe they’re just classifying all models into “reasoning models” eg o3 vs “... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		typs 44 days ago \| parent \| context \| favorite \| on: State of AI: An Empirical 100T Token Study with Op... I believe they’re just classifying all models into “reasoning models” eg o3 vs “non reasoning models” eg 4o and just doing a comparison of total tokens (input tokens + hidden reasoning output tokens + shown output tokens)

maikakz 44 days ago [–]

that's exactly right!

DIAexitNode 44 days ago | [–]

hell yeah, 109 out of 10 doors opened! 99 bonus doors! what are you talking about, man?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact